UPDATES • OpenClaw quick fix

ChatGPT/Codex route broke after update?

OpenClaw 2026.5.6 fixed a 2026.5.5 doctor --fix regression that could rewrite valid openai-codex/* ChatGPT/Codex OAuth routes to openai/*, breaking OAuth-only GPT-5.5 setups or moving users onto the API-key route. If your agents started failing right after that update, check the route before changing prompts or reinstalling.

In simple words: Make a safe copy if the step could change your setup, try the smallest check, then confirm OpenClaw is back to normal before doing more. The source link and commands stay below for people who want the technical detail.

Checklist

Confirm the symptom: failures started after running OpenClaw 2026.5.5 doctor --fix or a repair sequence around that release.

Restore the Codex OAuth default model route, then validate config.

Recovery command from the v2026.5.6 release note

openclaw models set openai-codex/gpt-5.5 && openclaw config validate

Before running agents again, verify the default model/auth path is back on openai-codex/gpt-5.5 and not an unintended openai/* API-key route.

Take a Safety Net snapshot before the next update or provider/auth change so you can roll back cleanly.

Success looks like

• Config validation passes after the model route is reset.

• The default agent uses the ChatGPT/Codex OAuth route again instead of an accidental OpenAI API-key route.

• You have a labeled pre-change snapshot before applying more repair/update commands.

Source: OpenClaw v2026.5.6 release note · link

Before the next risky OpenClaw change

Turn this quick fix into a repeatable rollback path.

If this touches tokens, providers, upgrades, plugins, or shared-agent settings, do the free check first — then use a verified snapshot and one restore drill before trusting unattended work again.

What OpenClaw Safety Net adds

pre-change snapshot checklist
restore-drill steps before the real incident
gateway/config smoke test before agents run again

Use the free fix when: you only need to unblock this one low-risk change and can write the backup label, smoke result, and rollback trigger in your own notes.

Buy when: this same risk will happen again, another person needs to repeat the fix, or you want a purchase-to-first-GREEN receipt, restore drill, and written rollback record before agents run unattended.

Do not buy yet if: you have not tried the free checklist, you need live support, or you are not ready to make a verified backup before changing a working setup.

Use OpenClaw Safety Net before the risky change →

Free fix first; buy the playbook only when the rollback path needs a repeatable first-GREEN proof record.

Have a high‑value nugget? Submit it.